111 citations · 184 across the 13 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Does task decomposition improve automatic NLG evaluation?
Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1
The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work seeks to i…
cs.CL2026
Post-hoc Alignment of LLM-judges to Human Judgment Distribution
Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1
The LLM-as-a-judge (LLMaJ) framework offers a cost-effective and reproducible solution for automatic evaluation. However, current evaluation practices typically compare LLMaJ judgm…